You are on page 1of 17

GROUP 4

CHAPTER 10 Dayal, Leah


Eiman, Russelle
Lancero, Ferlyn Joy ( Group 2 )

Between-Subjects Narciso, Pearl Hillary


Santiago, Louise Marreli
Sumayo, Quiarra
Factorial Design Stub Code 1292
More Than One Independent
Variable
Factorial Designs – designs in which we study two or more
independent variables at the same time.
Factors – independent variables in these designs.
Two-Factor Experiment – the simplest factorial design that has only
two factors.

– The results we get from this experiment give us two kinds of


information:
• Information about the effects of each independent variable in the
experiment.
• Enable us to answer this question: How does the influence of one
independent variable affect the influence of another in
experiment?
More Than One Independent
Variable Our plant study, for example, would have
two factors talking and music. We would
LOOKING want to know about the main effects of
both factors. A factorial experiment
FOR allows us to know if each factor alone
produces a significant effect on behavior.
MAIN EFFECTS
FACTOR 1:
MAIN EFFECT How much did changes in talking
affect plant growth?
- The action of a single independent
variable in an experiment; a change in FACTOR 2:
behavior associated with a change in the How much did changes in music
value of a single independent variable affect plant growth?
within the experiment.
More Than One Independent
Variable INTERACTION
- Present if the effect of one independent
variable changes across the levels of another
independent variable.
• When an interaction is present in a two-
L O OK IN G factor experiment, there is no complete
picture of the results of the experiment
F OR without considering both factors because
the effects of one factor will change
I NT E RA CTI ON S depending on the levels of the other.

• Interaction qualifies the main effects. It


tells that there could be limits or
exceptions to the main effects of one or
more factors.
More Than One Independent
Variable This is because these two substances
interact.
Higher-Order Interactions
- there are more than two independent
EXAMPLE : variables in a factorial experiment.
A couple of drinks at a party
can make you feel relaxed and In a three-factor experiment, it is
happy. If you are upset or possible to get an interaction among all
anxious, a sleeping pill Might three independent variables. The action
help you to sleep. Alone, a little of each factor could be influenced by
the values of the other two.
alcohol or a sleeping pill might
not Be especially harmful. But,
take the two together, And you EXAMPLE:
would end up dead or in a coma.
Driver experience, alcohol, and degree
of darkness could interact in causing
traffic accidents.
Laying Out a
DIAGRAMMING A DESIGN
Factorial Design MATRIX FOR THE TWO-FACTOR
EXPERIMENT:

INDICATE THE TWO


1. INDEPENDENT VARIABLES.

Design Matrix INDICATE THE LEVELS OF


2.
- t r a n s l a t i n g an idea a b o u t a n FACTOR 1.
experiment into a simple diagram. It
w i l l b e e a s i e r t o u n d e r s t a n d w hat b ein g
3. INDICATE THE LEVELS OF
teste d, wha t kin d of de sign to be u sed, FACTOR 2.
and the num be rs of c on diti ons required .
4 INDICATE THE FOUR
DIFFERENT TREATMENT
CONDITIONS.
Laying Out a Factorial Design
NAME EXPERIMENT
– Used in illustrating and describing
1.
factorial designs. It is a two-factor
experiment. This design can be written in
DESCRIBING shorthand form as a 2 x 2 factorial design.

THE
DESIGN SHORTHAND DESIGN
- A system that uses numbers to describe
the design of a factorial experiment.
Laying Out a Factorial
Design LIST the two factors in parentheses after
the numerical notation.

Names of each factor are placed in


parentheses following numerical notations.
FACTOR The name of the factor represented by the
first digit would be the first name you would
list; name
1. of the second factor would be
LABELING second.

METHODS
Just like in shorthand notation, factor labels
are separated by by x.

The experiment is a between-subject factorial design when different


subjects are assigned to each of the four treatment conditions.
Laying Out a Factorial Design
Example 1: Example 2:
2 x 2 (type of Name x Length 2 (type of name) x 2 (length
of Name) between-subject of name) between-subject
factorial design factorial design
FACTOR
It can also be expanded to LABELING It can also be expanded to
include factor levels: include factor levels:
METHODS
Example 3: Example 4:
2 x 2 ( Type of Name: Given, 2 ( given name or nickname)
nickname x Length of name: x 2 (short or long name)
Short, Long) between-subject between subject design
factorial designs
Laying Out a Factorial Design
Step 4:
FACTOR 1
Indicate the four treatment (TYPE OF NAME)
conditions.

Given Name Nickname

Short Short
Short
Given Name Nickname
FACTOR 2
(LENGTH OF NAME)
Long Long
Long
Given Name
Nickname
A Research Example

Understanding Effects from Factorial


Designs

Crossover Interaction - The effects of each


factor completely reverse at each level of the
factor
.
Choosing a Between-
Subjects Design
• Keep your first experiment • Subjects are usually
simple. Focus on the assigned to each of the
variables that are critical. treatment conditions at
random.

In a two-factor between two subjects design, there


can only be three possible effects: a main effect for
each factor and an interaction between the two
factors (total = three possible effects).
Choosing a Between-
Subjects Design
Example:
Let’s use A, B, and C to represent three factors in an experiment.

 Main Effect:  Each pair of factors can interact


a main effect for A interactions between A and B
a main effect for B interactions between A and C
a main effect for C interactions between B and C
Choosing a Between-
Subjects Design
 All Three Factors Can Interact: interaction among A, B, and
C

 To add up all the possible significant effects, the total equals


7.
Choosing a Between-
Subjects Design
Questions to Ask When Designing a Between-Subjects

Experiment (From Top to Bottom) Practical Limitations on Using


Factorial Designs:
• Often require many subjects.
• Can be time-consuming
• Require more statistical procedures
than do other designs
(interpretability of results).
REFERENCE:

Myers, A. & Hansen, C. (2012).


Experimental Psychology, 7th Ed. 7th ed.,
Belmont, Ca, Wadsworth Cengage

You might also like